arXiv subjects

Honggen Zhang

Publications and source records attributed to Honggen Zhang.

5 recordsLinked to original sources

arXiv2025

siDPT: siRNA Efficacy Prediction via Debiased Preference-Pair Transformer

Small interfering RNA (siRNA) is a short double-stranded RNA molecule (about 21-23 nucleotides) with the potential to cure diseases by silencing the function of target genes. Due to its well-understood mechanism, many siRNA-based drugs have been evaluated in clinical trials. However, selecting effective binding regions and designing siRNA sequences requires extensive experimentation, making the process costly. As genomic resources and publicly available siRNA datasets continue to grow, data-driven models can be leveraged to better understand siRNA-mRNA interactions. To fully exploit such data, curating high-quality siRNA datasets is essential to minimize experimental errors and noise. We propose siDPT: siRNA efficacy Prediction via Debiased Preference-Pair Transformer, a framework that constructs a preference-pair dataset and designs an siRNA-mRNA interactive transformer with debiased ranking objectives to improve siRNA inhibition prediction and generalization. We evaluate our approach using two public datasets and one newly collected patent dataset. Our model demonstrates substantial improvement in Pearson correlation and strong performance across other metrics.

q-bio.GN↗

arXiv2024

REAL: Response Embedding-based Alignment for LLMs

Aligning large language models (LLMs) to human preferences is a crucial step in building helpful and safe AI tools, which usually involve training on supervised datasets. Popular algorithms such as Direct Preference Optimization (DPO) rely on pairs of AI-generated responses ranked according to human annotation. The response pair annotation process might bring human bias. Building a correct preference dataset is the costly part of the alignment pipeline. To improve annotation efficiency and quality in the LLMs alignment, we propose REAL: Response Embedding-based Alignment for LLMs, a strategy for constructing a high-quality training dataset that focuses on acquiring the less ambiguous preference pairs for labeling out of a set of response candidates. Our selection process is based on the similarity of embedding responses independently of prompts, which guarantees the selection process in an off-policy setting, avoiding adaptively measuring the similarity during the training. Experimental results on real-world dataset SHP2 and synthetic HH-RLHF benchmarks indicate that choosing dissimilar response pairs enhances the direct alignment of LLMs while reducing inherited labeling errors. The model aligned with dissimilar response pairs obtained a better margin and win rate on the dialogue task. Our findings suggest that focusing on distinct pairs can reduce the label error and improve LLM alignment efficiency, saving up to $65\%$ of annotators' work.

cs.CL↗

arXiv2024

mRNA2vec: mRNA Embedding with Language Model in the 5'UTR-CDS for mRNA Design

Messenger RNA (mRNA)-based vaccines are accelerating the discovery of new drugs and revolutionizing the pharmaceutical industry. However, selecting particular mRNA sequences for vaccines and therapeutics from extensive mRNA libraries is costly. Effective mRNA therapeutics require carefully designed sequences with optimized expression levels and stability. This paper proposes a novel contextual language model (LM)-based embedding method: mRNA2vec. In contrast to existing mRNA embedding approaches, our method is based on the self-supervised teacher-student learning framework of data2vec. We jointly use the 5' untranslated region (UTR) and coding sequence (CDS) region as the input sequences. We adapt our LM-based approach specifically to mRNA by 1) considering the importance of location on the mRNA sequence with probabilistic masking, 2) using Minimum Free Energy (MFE) prediction and Secondary Structure (SS) classification as additional pretext tasks. mRNA2vec demonstrates significant improvements in translation efficiency (TE) and expression level (EL) prediction tasks in UTR compared to SOTA methods such as UTR-LM. It also gives a competitive performance in mRNA stability and protein production level tasks in CDS such as CodonBERT.

q-bio.QM↗

arXiv2023

HaSa: Hardness and Structure-Aware Contrastive Knowledge Graph Embedding

We consider a contrastive learning approach to knowledge graph embedding (KGE) via InfoNCE. For KGE, efficient learning relies on augmenting the training data with negative triples. However, most KGE works overlook the bias from generating the negative triples-false negative triples (factual triples missing from the knowledge graph). We argue that the generation of high-quality (i.e., hard) negative triples might lead to an increase in false negative triples. To mitigate the impact of false negative triples during the generation of hard negative triples, we propose the Hardness and Structure-aware (\textbf{HaSa}) contrastive KGE method, which alleviates the effect of false negative triples while generating the hard negative triples. Experiments show that HaSa improves the performance of InfoNCE-based KGE approaches and achieves state-of-the-art results in several metrics for WN18RR datasets and competitive results for FB15k-237 datasets compared to both classic and pre-trained LM-based KGE methods.

cs.AI↗

arXiv2022

How News Evolves? Modeling News Text and Coverage using Graphs and Hawkes Process

Monitoring news content automatically is an important problem. The news content, unlike traditional text, has a temporal component. However, few works have explored the combination of natural language processing and dynamic system models. One reason is that it is challenging to mathematically model the nuances of natural language. In this paper, we discuss how we built a novel dataset of news articles collected over time. Then, we present a method of converting news text collected over time to a sequence of directed multi-graphs, which represent semantic triples (Subject -> Predicate} ->Object). We model the dynamics of specific topological changes in these graphs using a set of multivariate count series, which we fit the discrete-time Hawkes process. With our real-world data, we show that the multivariate time series contain both dynamic information of how many articles/words were published each day and semantic information of the content of the articles. This yields novel insights into how news events are covered. We show with the experiment that our approach can be used to infer from a sequence of news articles if the articles were published by major or entertainment news outlets.

cs.CL↗